Instructions to use TheBloke/stablecode-completion-alpha-3b-4k-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/stablecode-completion-alpha-3b-4k-GPTQ with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="TheBloke/stablecode-completion-alpha-3b-4k-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/stablecode-completion-alpha-3b-4k-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/stablecode-completion-alpha-3b-4k-GPTQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/stablecode-completion-alpha-3b-4k-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/stablecode-completion-alpha-3b-4k-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/stablecode-completion-alpha-3b-4k-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/stablecode-completion-alpha-3b-4k-GPTQ

SGLang

How to use TheBloke/stablecode-completion-alpha-3b-4k-GPTQ with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "TheBloke/stablecode-completion-alpha-3b-4k-GPTQ" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/stablecode-completion-alpha-3b-4k-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "TheBloke/stablecode-completion-alpha-3b-4k-GPTQ" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/stablecode-completion-alpha-3b-4k-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/stablecode-completion-alpha-3b-4k-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/stablecode-completion-alpha-3b-4k-GPTQ
```

TheBloke commited on Aug 8, 2023

Commit

1f15b29

1 Parent(s): ec53fd9

Initial GPTQ model commit

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -96,9 +96,9 @@ All GPTQ files are made with AutoGPTQ.
 | [main](https://huggingface.co/TheBloke/stablecode-completion-alpha-3b-4k-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | 1.82 GB | No | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
 | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/stablecode-completion-alpha-3b-4k-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | 1.96 GB | No | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
 | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/stablecode-completion-alpha-3b-4k-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | 1.86 GB | No | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
-| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/stablecode-completion-alpha-3b-4k-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | Processing, coming soon | No | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
-| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/stablecode-completion-alpha-3b-4k-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | Processing, coming soon | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |
-| [gptq-8bit-64g-actorder_True](https://huggingface.co/TheBloke/stablecode-completion-alpha-3b-4k-GPTQ/tree/gptq-8bit-64g-actorder_True) | 8 | 64 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | Processing, coming soon | No | 8-bit, with group size 64g and Act Order for maximum inference quality. Poor AutoGPTQ CUDA speed. |
 ## How to download from branches

 | [main](https://huggingface.co/TheBloke/stablecode-completion-alpha-3b-4k-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | 1.82 GB | No | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
 | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/stablecode-completion-alpha-3b-4k-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | 1.96 GB | No | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
 | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/stablecode-completion-alpha-3b-4k-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | 1.86 GB | No | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
+| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/stablecode-completion-alpha-3b-4k-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | 1.82 GB | No | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
+| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/stablecode-completion-alpha-3b-4k-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | 3.08 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |
+| [gptq-8bit-64g-actorder_True](https://huggingface.co/TheBloke/stablecode-completion-alpha-3b-4k-GPTQ/tree/gptq-8bit-64g-actorder_True) | 8 | 64 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | 3.14 GB | No | 8-bit, with group size 64g and Act Order for maximum inference quality. Poor AutoGPTQ CUDA speed. |
 ## How to download from branches